© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10616
    Prev
    Next
    INDEX
    Explanations

    names followed by pauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -1.38
     póster
    -1.37
     Mě
    -1.35
    Württemberg
    -1.31
     to
    -1.30
    UCIÓN
    -1.28
     tiga
    -1.27
     certamen
    -1.27
    )։
    -1.27
    нял
    -1.26
    POSITIVE LOGITS
    2
    1.59
     irgend
    1.53
    Preparazione
    1.45
    1
    1.38
     associated
    1.37
     photolibrary
    1.35
     ergän
    1.32
     シャツ
    1.32
     vorliegenden
    1.32
     cardin
    1.31
    Activations Density 0.007%

    No Known Activations